Occupancy Grid Mapping With Side-Information Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional occupancy grid mapping techniques fail to exploit features of automotive environments, such as sparsity of occupancy or clustering of occupied cells, leading to inefficiencies and high false positive rates in obstacle detection.
Innovation Solution
An automotive system that utilizes side information, including camera images, previously generated OGMs, and digital maps, in addition to primary ToF transceiver data, to generate occupancy grid maps using Sparse Bayesian Learning (SBL) or Bayesian Generalized Kernel (BGK) models, enhancing detection likelihood and reducing false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional occupancy grid mapping techniques are used, then the mapping process is simple, but the false positive rate is high and detection accuracy is poor
Solution Approach 1:
The patent combines multiple data sources including TOF transceiver data, camera images, digital maps, and previously generated OGMs into a unified occupancy grid mapping system. This merging of multiple information sources allows the system to leverage complementary strengths of each data type to improve detection accuracy while reducing false positives, directly resolving the contradiction between simple mapping and high detection accuracy.
Solution Approach 2:
The system employs a multi-functional approach where a single occupancy grid map integrates information from various sensors and data types. The mapping model processes TOF data, camera images, digital maps, and historical OGMs simultaneously, creating a universal representation of the environment that serves multiple detection and navigation functions, thereby improving accuracy without requiring separate specialized systems.
2Reliability
If more data sources are integrated, then detection likelihood increases, but processing complexity increases
Solution Approach 1:
The system performs preliminary processing of multiple data sources before integrating them into the final occupancy grid map. Camera images, digital maps, and TOF data are pre-processed and aligned with previously generated OGMs to establish a consistent coordinate system and reference frame. This preliminary action reduces the complexity of subsequent integration by preparing data in advance in a standardized format, enabling reliable multi-source fusion without overwhelming processing complexity.
Solution Approach 2:
The patent incorporates feedback mechanisms by using previously generated occupancy grid maps as input for creating new maps. The system continuously refines its understanding of the environment by comparing current sensor data with historical OGMs, allowing it to learn from past detections and corrections. This feedback loop improves detection likelihood by leveraging accumulated knowledge while managing processing complexity through iterative refinement rather than requiring complete reprocessing of all data.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The proposed method improves obstacle detection accuracy by leveraging side information, resulting in reduced false positive rates and increased detection likelihood compared to conventional methods.
Implementation Method 1
transmit signals, receive reflected signals corresponding to reflections of the transmitted signals by one or more objects
Implementation Method 2
Light Detection and Ranging (LiDAR) data
Implementation Method 3
transmit signals, receive reflected signals corresponding to reflections of the transmitted signals
Data Source
AI summary
The present disclosure relates to systems and methods for occupancy grid mapping. In one or more embodiments, a system includes a detection and ranging system configured to transmit signals, receive reflected signals corresponding to reflections of the transmitted signals by objects in an environment around the detection and ranging system, and generate point cloud data indicating positions of the objects, computer-readable memory configured to store side information, which can one or more digital maps, images of the environment, or previously generated occupancy grid maps, and processing circuitry configured to receive the point cloud data from the detection and ranging system, receive the side information from the computer-readable memory, determine hyperparameters for a mapping model based on the side information, and process the point cloud data using the mapping model using the hyperparameters to generate an occupancy grid map of the environment.